annahdo / implementing_activation_steeringLinks
A collection of different ways to implement accessing and modifying internal model activations for LLMs
☆19Updated last year
Alternatives and similar repositories for implementing_activation_steering
Users that are interested in implementing_activation_steering are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Experiments with representation engineering☆13Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆226Updated 11 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆94Updated 2 years ago
- ☆36Updated last year
- ☆131Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆212Updated this week
- A library for efficient patching and automatic circuit discovery.☆79Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆128Updated 8 months ago
- ☆252Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆222Updated last week
- ☆29Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- Inference API for many LLMs and other useful tools for empirical research☆79Updated this week
- Erasing concepts from neural representations with provable guarantees☆239Updated 9 months ago
- Algebraic value editing in pretrained language models☆66Updated 2 years ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 3 weeks ago
- ☆24Updated last year
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- ☆129Updated last year
- ☆281Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆192Updated last year
- ☆92Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆140Updated 4 months ago
- ☆30Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆28Updated 2 weeks ago
- Unified access to Large Language Model modules using NNsight☆58Updated this week